© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3731
    Prev
    Next
    INDEX
    Explanations

    the pronoun "I" and its variations in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    i.e

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ","");
    -0.60
    Controllo
    -0.54
    ="#"><
    -0.50
    torn
    -0.50
    CloseOperation
    -0.49
     redor
    -0.49
    ★★★★☆
    -0.48
    Erst
    -0.48
     onlyOwner
    -0.47
    "";
    -0.47
    POSITIVE LOGITS
    httphttps
    0.69
     الحره
    0.68
    ніципалі
    0.67
     насељу
    0.66
    pso
    0.65
     iVar
    0.64
     iArr
    0.61
    tagHelper
    0.60
     ویکی‌پدیا
    0.59
    EndContext
    0.59
    Activations Density 0.036%

    No Known Activations